pytorch_sparse
pytorch_sparse copied to clipboard
rusty1s
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Hi, thank you for your time on developing this project. I have a question that I think is rather simple: Why do you have to enforce that the SparseStorage's col...
Dear authors, Thank you for developing such a great library. I'm writing to ask about the time complexity of the sparse-sparse matrix multiplication implemented in this library. Suppose the sizes...
System : Windows 10 OS Conda : 23.9.0 GPU : NVIDIA RTX 3060 Laptop I got a venv with python==3.8.15 and installed the following ```py pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0...
I ran this on kaggle notebook: !pip install torch_geometric !pip install torch-scatter==2.1.1 torch-sparse==0.6.17 -f https://data.pyg.org/whl/torch-2.0.0+cu118.html And it said Installing collected packages: torch-scatter, torch-sparse Successfully installed torch-scatter-2.1.1+pt20cu118 torch-sparse-0.6.17+pt20cu118 And then I...
I have recently reinstalled pytorch_geometric and pytorch_sparse. After installing version 2.4.0, I get the following warning when I import pytorch_geometric ``` /path/to/.conda/envs/gnn/lib/python3.10/site-packages/torch_geometric/typing.py:101: UserWarning: An issue occurred while importing 'torch-sparse'. Disabling...
Hello, I'm having some issues correctly installing pytorch sparse with METIS support on a Mac with apple silicon. I'm trying to install for pytorch 2.1.0, without any CUDA support. Initially,...
Hello, is there any way to do element-wise matrix multiplication with your library? Thank you very much!
For `torch_sparse.SparseTensor` wrapped in `nn.DataParallel`, they will not be automatically replicated to each of the target devices -- they remains on the master GPU. I tested on RTX A6000 with...
Hi, thanks very much for developing this useful library! I have no issue running the sparse multiplication on CPU. However, when I tried to run it on the CUDA, it...
Hi! I am trying to get an installation running on an HPC cluster with somewhat older dependencies. I have found torch 1.8.0 with CUDA 11.1 to work, so now I...
